Give the user the option to override where model weights are stored (#232)

Browse Source

* Give the user the option to override where model weights are stored

* Fix ggml_nbytes() problem and cleanup

For a tensor with zero elements ggml_nbytes() was returning
uint64_t::max, and this was causing graph allocation failure.

* Add timing info to CUDA graph evaluation

* Add more timing info

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

...

This commit is contained in:

Kawrakow

2025-02-25 17:55:58 +02:00

committed by GitHub

parent 547eee81d9

commit 94b659a2f1

9 changed files with 848 additions and 621 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1302

src/llama.cpp

File diff suppressed because it is too large Load Diff